© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6718
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical stress and forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical details about mechanical forces, stress, and mechanical testing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    words and variables related to physical forces in scientific or engineering contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    descriptions and calculations of mechanical forces and stresses in technical/engineering contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    technical or mathematical descriptions of forces and physical stresses in engineering or physics contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.71
    RTSC
    -0.63
     udaler
    -0.62
     indígen
    -0.61
    期刊论文
    -0.60
    ۠
    -0.59
     Dieſe
    -0.57
     NavController
    -0.57
    оргаш
    -0.57
    dollis
    -0.57
    POSITIVE LOGITS
     force
    0.81
     forces
    0.70
    force
    0.66
     pressure
    0.65
     Force
    0.62
    Force
    0.59
    pressure
    0.58
    forces
    0.57
     lực
    0.54
    力
    0.53
    Activations Density 0.330%

    No Known Activations